Paper
Proposition of Method of Conceptual Filtering Using Iterative Knowledge Creation
- Authors:
- Krzysztof Wójcik
- Abstract
- The main goal of this article is to describe briefly an image processing method utilizing the iterative OTO (Observation-Transformation-Operation) scheme, which creates the knowledge about images under consideration. The general knowledge structure, which may be regarded as a simple ontology, is built by the help of the inductive learning methods and some classes of knowledge transformations. The paper describes basic kinds of these transformations. The article presents an example of the practical usage of the proposed scheme in the chosen, relatively simple, task of image processing. In this context the proposed approach, which can be called “conceptual filtering”, may be considered as a variant of Syntactic Image Understanding methods. Additionally, the prospect of the application of the OTO scheme in various kinds of identification and classification tasks is proposed. As a conclusion, the article points to a main condition of a successful usage of the described methodology, namely reducing the size of the hypothesis space which may be done by the removal of the unused concepts and objects, and the usage of the operations of knowledge structure joining.
- Keywords
- Image Processing; Pattern Recognition; Machine Learning
- StartPage
- 18
- EndPage
- 26
- Doi